def run_audio(dataset):
log.info("Creating RNN-GSN for dataset %s!", dataset)
outdir = "outputs/rnngsn/%s/" % dataset
# grab the dataset
if dataset == 'tedlium':
dataset = tedlium.TEDLIUMDataset(max_speeches=3)
extra_args = {
}
elif dataset == 'codegolf':
dataset = codegolf.CodeGolfDataset()
extra_args = {
}
else:
raise ValueError("dataset %s not recognized." % dataset)
rng = numpy.random.RandomState(1234)
mrg = RandomStreams(rng.randint(2 ** 30))
assert dataset.window_size == 256, dataset.window_size
rnngsn = RNN_GSN(layers=2,
walkbacks=4,
input_size=dataset.window_size,
image_height = 1,
image_width = 256,
hidden_size=128,
rnn_hidden_size=128,
weights_init='gaussian',
weights_std=0.01,
rnn_weights_init='identity',
rnn_hidden_activation='relu',
rnn_weights_std=0.0001,
mrg=mrg,
outdir=outdir, **extra_args)
# make an optimizer to train it
optimizer = AdaDelta(model=rnngsn,
dataset=dataset,
epochs=200,
batch_size=128,
min_batch_size=2,
learning_rate=1e-6,
save_freq=1,
stop_patience=100)
ll = Monitor('crossentropy', rnngsn.get_monitors()['noisy_recon_cost'],test=True)
mse = Monitor('frame-error', rnngsn.get_monitors()['mse'],train=True,test=True,valid=True)
plot = Plot(
bokeh_doc_name='rnngsn_tedlium_%s'%dataset, monitor_channels=[ll,mse],open_browser=True
)
# perform training!
optimizer.train(plot=plot)
# use the generate function!
generated, _ = rnngsn.generate(initial=None, n_steps=200)
# Construct image from the weight matrix
image = Image.fromarray(
tile_raster_images(
X=rnngsn.weights_list[0].get_value(borrow=True).T,
img_shape=closest_to_square_factors(rnngsn.input_size),
tile_shape=closest_to_square_factors(rnngsn.hidden_size),
tile_spacing=(1, 1)
)
)
image.save(outdir + 'rnngsn_%s_weights.png'%(dataset,))
log.debug("done!")
del rnngsn
del optimizer
if has_pylab:
pylab.show()
def run_sequence(sequence=0):
log.info("Creating RNN-GSN for sequence %d!" % sequence)
# grab the MNIST dataset
mnist = MNIST(sequence_number=sequence, concat_train_valid=True)
outdir = "outputs/rnngsn/mnist_%d/" % sequence
rng = numpy.random.RandomState(1234)
mrg = RandomStreams(rng.randint(2**30))
rnngsn = RNN_GSN(layers=2,
walkbacks=4,
input_size=28 * 28,
hidden_size=1000,
tied_weights=True,
rnn_hidden_size=100,
weights_init='uniform',
weights_interval='montreal',
rnn_weights_init='identity',
mrg=mrg,
outdir=outdir)
# load pretrained rbm on mnist
# rnngsn.load_gsn_params('outputs/trained_gsn_epoch_1000.pkl')
# make an optimizer to train it (AdaDelta is a good default)
optimizer = AdaDelta(model=rnngsn,
dataset=mnist,
n_epoch=200,
batch_size=100,
minimum_batch_size=2,
learning_rate=1e-6,
save_frequency=1,
early_stop_length=200)
# optimizer = SGD(model=rnngsn,
# dataset=mnist,
# n_epoch=300,
# batch_size=100,
# minimum_batch_size=2,
# learning_rate=.25,
# lr_decay='exponential',
# lr_factor=.995,
# momentum=0.5,
# nesterov_momentum=True,
# momentum_decay=False,
# save_frequency=20,
# early_stop_length=100)
crossentropy = Monitor('crossentropy',
rnngsn.get_monitors()['noisy_recon_cost'],
test=True)
error = Monitor('error', rnngsn.get_monitors()['mse'], test=True)
# perform training!
optimizer.train(monitor_channels=[crossentropy, error])
# use the generate function!
log.debug("generating images...")
generated, ut = rnngsn.generate(initial=None, n_steps=400)
# Construct image
image = Image.fromarray(
tile_raster_images(X=generated,
img_shape=(28, 28),
tile_shape=(20, 20),
tile_spacing=(1, 1)))
image.save(outdir + "rnngsn_mnist_generated.png")
log.debug('saved generated.png')
# Construct image from the weight matrix
image = Image.fromarray(
tile_raster_images(X=rnngsn.weights_list[0].get_value(borrow=True).T,
img_shape=(28, 28),
tile_shape=closest_to_square_factors(
rnngsn.hidden_size),
tile_spacing=(1, 1)))
image.save(outdir + "rnngsn_mnist_weights.png")
log.debug("done!")
del mnist
del rnngsn
del optimizer
def run_midi(dataset):
log.info("Creating RNN-GSN for dataset %s!", dataset)
outdir = "outputs/rnngsn/%s/" % dataset
# grab the MIDI dataset
if dataset == 'nottingham':
midi = Nottingham()
elif dataset == 'jsb':
midi = JSBChorales()
elif dataset == 'muse':
midi = MuseData()
elif dataset == 'piano_de':
midi = PianoMidiDe()
else:
raise AssertionError("dataset %s not recognized." % dataset)
# rng = numpy.random
# rng.seed(0xbeef)
# mrg = RandomStreams(seed=rng.randint(1 << 30))
rng = numpy.random.RandomState(1234)
mrg = RandomStreams(rng.randint(2 ** 30))
rnngsn = RNN_GSN(layers=2,
walkbacks=4,
input_size=88,
hidden_size=150,
rnn_hidden_size=100,
weights_init='gaussian',
weights_std=0.01,
rnn_weights_init='identity',
rnn_hidden_activation='relu',
rnn_weights_std=0.0001,
mrg=mrg,
outdir=outdir)
# make an optimizer to train it
optimizer = AdaDelta(model=rnngsn,
dataset=midi,
n_epoch=200,
batch_size=100,
minimum_batch_size=2,
# learning_rate=1e-4,
learning_rate=1e-6,
save_frequency=1,
early_stop_length=100)
ll = Monitor('crossentropy', rnngsn.get_monitors()['noisy_recon_cost'],test=True)
mse = Monitor('frame-error', rnngsn.get_monitors()['mse'],train=True,test=True,valid=True)
plot = Plot(bokeh_doc_name='rnngsn_midi_%s'%dataset, monitor_channels=[ll,mse],open_browser=True)
# perform training!
optimizer.train(plot=plot)
# use the generate function!
generated, _ = rnngsn.generate(initial=None, n_steps=200)
dt = 0.3
r = (21, 109)
midiwrite(outdir + 'rnngsn_generated_midi.mid', generated, r=r, dt=dt)
if has_pylab:
extent = (0, dt * len(generated)) + r
pylab.figure()
pylab.imshow(generated.T, origin='lower', aspect='auto',
interpolation='nearest', cmap=pylab.cm.gray_r,
extent=extent)
pylab.xlabel('time (s)')
pylab.ylabel('MIDI note number')
pylab.title('generated piano-roll')
# Construct image from the weight matrix
image = Image.fromarray(
tile_raster_images(
X=rnngsn.weights_list[0].get_value(borrow=True).T,
img_shape=closest_to_square_factors(rnngsn.input_size),
tile_shape=closest_to_square_factors(rnngsn.hidden_size),
tile_spacing=(1, 1)
)
)
image.save(outdir + 'rnngsn_midi_weights.png')
log.debug("done!")
del midi
del rnngsn
del optimizer
if has_pylab:
pylab.show()
def run_sequence(sequence=0):
log.info("Creating RNN-GSN for sequence %d!" % sequence)
# grab the MNIST dataset
mnist = MNIST(sequence_number=sequence, concat_train_valid=True)
outdir = "outputs/rnngsn/mnist_%d/" % sequence
rng = numpy.random.RandomState(1234)
mrg = RandomStreams(rng.randint(2 ** 30))
rnngsn = RNN_GSN(layers=2,
walkbacks=4,
input_size=28 * 28,
hidden_size=1000,
tied_weights=True,
rnn_hidden_size=100,
weights_init='uniform',
weights_interval='montreal',
rnn_weights_init='identity',
mrg=mrg,
outdir=outdir)
# load pretrained rbm on mnist
# rnngsn.load_gsn_params('outputs/trained_gsn_epoch_1000.pkl')
# make an optimizer to train it (AdaDelta is a good default)
optimizer = AdaDelta(model=rnngsn,
dataset=mnist,
n_epoch=200,
batch_size=100,
minimum_batch_size=2,
learning_rate=1e-6,
save_frequency=1,
early_stop_length=200)
# optimizer = SGD(model=rnngsn,
# dataset=mnist,
# n_epoch=300,
# batch_size=100,
# minimum_batch_size=2,
# learning_rate=.25,
# lr_decay='exponential',
# lr_factor=.995,
# momentum=0.5,
# nesterov_momentum=True,
# momentum_decay=False,
# save_frequency=20,
# early_stop_length=100)
crossentropy = Monitor('crossentropy', rnngsn.get_monitors()['noisy_recon_cost'], test=True)
error = Monitor('error', rnngsn.get_monitors()['mse'], test=True)
# perform training!
optimizer.train(monitor_channels=[crossentropy, error])
# use the generate function!
log.debug("generating images...")
generated, ut = rnngsn.generate(initial=None, n_steps=400)
# Construct image
image = Image.fromarray(
tile_raster_images(
X=generated,
img_shape=(28, 28),
tile_shape=(20, 20),
tile_spacing=(1, 1)
)
)
image.save(outdir + "rnngsn_mnist_generated.png")
log.debug('saved generated.png')
# Construct image from the weight matrix
image = Image.fromarray(
tile_raster_images(
X=rnngsn.weights_list[0].get_value(borrow=True).T,
img_shape=(28, 28),
tile_shape=closest_to_square_factors(rnngsn.hidden_size),
tile_spacing=(1, 1)
)
)
image.save(outdir + "rnngsn_mnist_weights.png")
log.debug("done!")
del mnist
del rnngsn
del optimizer
def run_midi(dataset):
log.info("Creating RNN-GSN for dataset %s!", dataset)
outdir = "outputs/rnngsn/%s/" % dataset
# grab the MIDI dataset
if dataset == 'nottingham':
midi = Nottingham()
elif dataset == 'jsb':
midi = JSBChorales()
elif dataset == 'muse':
midi = MuseData()
elif dataset == 'piano_de':
midi = PianoMidiDe()
else:
raise AssertionError("dataset %s not recognized." % dataset)
# rng = numpy.random
# rng.seed(0xbeef)
# mrg = RandomStreams(seed=rng.randint(1 << 30))
rng = numpy.random.RandomState(1234)
mrg = RandomStreams(rng.randint(2 ** 30))
rnngsn = RNN_GSN(layers=2,
walkbacks=4,
input_size=88,
hidden_size=150,
rnn_hidden_size=100,
weights_init='gaussian',
weights_std=0.01,
rnn_weights_init='identity',
rnn_hidden_activation='relu',
rnn_weights_std=0.0001,
mrg=mrg,
outdir=outdir)
# make an optimizer to train it
optimizer = AdaDelta(model=rnngsn,
dataset=midi,
epochs=200,
batch_size=100,
min_batch_size=2,
# learning_rate=1e-4,
learning_rate=1e-6,
save_freq=1,
stop_patience=100)
ll = Monitor('crossentropy', rnngsn.get_monitors()['noisy_recon_cost'],test=True)
mse = Monitor('frame-error', rnngsn.get_monitors()['mse'],train=True,test=True,valid=True)
plot = Plot(bokeh_doc_name='rnngsn_midi_%s'%dataset, monitor_channels=[ll,mse],open_browser=True)
# perform training!
optimizer.train(plot=plot)
# use the generate function!
generated, _ = rnngsn.generate(initial=None, n_steps=200)
dt = 0.3
r = (21, 109)
midiwrite(outdir + 'rnngsn_generated_midi.mid', generated, r=r, dt=dt)
if has_pylab:
extent = (0, dt * len(generated)) + r
pylab.figure()
pylab.imshow(generated.T, origin='lower', aspect='auto',
interpolation='nearest', cmap=pylab.cm.gray_r,
extent=extent)
pylab.xlabel('time (s)')
pylab.ylabel('MIDI note number')
pylab.title('generated piano-roll')
# Construct image from the weight matrix
image = Image.fromarray(
tile_raster_images(
X=rnngsn.weights_list[0].get_value(borrow=True).T,
img_shape=closest_to_square_factors(rnngsn.input_size),
tile_shape=closest_to_square_factors(rnngsn.hidden_size),
tile_spacing=(1, 1)
)
)
image.save(outdir + 'rnngsn_midi_weights.png')
log.debug("done!")
del midi
del rnngsn
del optimizer
if has_pylab:
pylab.show()
